© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117436
    Prev
    Next
    INDEX
    Explanations

    quotes and sayings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     должна
    -0.06
     контроль
    -0.06
    =!
    -0.06
     ngang
    -0.06
    ാനി
    -0.06
     официа
    -0.06
    新聞
    -0.06
     jeu
    -0.06
    ood
    -0.05
     результаты
    -0.05
    POSITIVE LOGITS
     VERY
    0.07
     rất
    0.07
     väldigt
    0.07
     veldig
    0.06
     poprzed
    0.06
     Japan
    0.06
     foarte
    0.06
     那
    0.06
     Pleistocene
    0.06
     sangat
    0.06
    Activations Density 0.024%

    No Known Activations